Sequential Feature Filtering Classifier [article]

Minseok Seo, Jaemin Lee, Jongchan Park, Dong-Geol Choi
2020 arXiv   pre-print
We propose Sequential Feature Filtering Classifier (FFC), a simple but effective classifier for convolutional neural networks (CNNs). With sequential LayerNorm and ReLU, FFC zeroes out low-activation units and preserves high-activation units. The sequential feature filtering process generates multiple features, which are fed into a shared classifier for multiple outputs. FFC can be applied to any CNNs with a classifier, and significantly improves performances with negligible overhead. We
more » ... vely validate the efficacy of FFC on various tasks: ImageNet-1K classification, MS COCO detection, Cityscapes segmentation, and HMDB51 action recognition. Moreover, we empirically show that FFC can further improve performances upon other techniques, including attention modules and augmentation techniques. The code and models will be publicly available.
arXiv:2006.11808v1 fatcat:hmn2ctq2ifapjn5his5fqggltq